AI Image Prompts · 绘画提示词库

based on the attached image,
generate a Side by side photo of a close up face, and half body character design (both views are different view of an identical design) of a woman with long, flowing dark hair and a gentle, warm smile. Her face is adorned with delicate freckles, and her striking blue almond-shaped eyes exude kindness. She wears an ornate, deep-blue hooded cloak embellished with intricate gold patterns resembling swirling waves or dragons, evoking a sense of fantasy or ancient nobility. The fabric appears rich and textured, fastened with an elaborate golden clasp at the shoulder. Underneath, glimpses of armored plating suggest a warrior or royal status. The overall aesthetic blends elegance with strength, set against a soft, neutral background that highlights her serene yet powerful presence. close up face on the left, half body on the right, on a flat plain white background, photography with edge lighting for depth, 16:9, 2K

Production of a low-poly image of a character figure utilizing NanoBanana, specifically a {argument name="character model" default="Megami Device"} model.

A single square image divided into a clean 3x3 grid of nine equal squares.
Each square contains the girl character from image1, close-up portrait, head and neck only, face filling most of the frame.

Each square has a different eyes.
Place the Japanese text below the each square as a label, not touching the edges.

1：Spiral eyes: {argument name="eye 1" default="spiral-only eyes"}
2：Blank eyes: {argument name="eye 2" default="blank eyes"}
3：Hollow eyes: {argument name="eye 3" default="hollow eyes"}
4：腫れた目: puffy eyes
5：不気味な目: creepy eyes
6：狂気の目: crazy eyes
7：誘惑的な目: mesmerizing eyes
8：色っぽい目: sensual eyes
9：機械の目: mechanical eyes

Simple blue background colors.
High resolution. Sticker sheet layout, perfect 3x3 alignment.

Please create a single, six-panel image of the woman in this picture, showing her from the {argument name="viewpoints" default="top, bottom, right, left, front, and back"} viewpoints.

Generate a character with Nano Banana. Tokimeki Memorial style.

A 2x2 grid of 4 monumental mathematical symbols carved as colossal terrain typography in an arid landscape

 [Top Left: “∫” as a canyon-cut arch in sandstone, a thin aqueduct stream following the curve, tiny caravans casting long shadows] [Top Right: “Σ” as a stepped fortress carved into a mesa, sharp terraces, windblown sand pooling in corners, micro equations chiseled in] [Bottom Left: “π” as massive stone pylons connected by a lintel bridge, ruined blocks scattered like proof fragments] [Bottom Right: Penrose Triangle as impossible ruins half-buried, forced perspective illusion, harsh sunlight slicing edges] 

Aerial oblique shot, golden hour desert light, crisp dramatic shadows, photoreal erosion detail, minimal haze, swiss 2x2 grid composition.

<instructions>    Input Variable:   [INSERT TOPIC HERE] (e.g., History of Space Exploration)

  System Instruction:  
Generate a crowded, hyper-realistic   "Book Nook" Diorama  . Use the following logic to procedurally fill the scene with high-density detail:

  1. Semantic Analysis (The Loot Table):  
      The Totem:   Identify the single tallest, most vertical object representing the topic (e.g., Saturn V Rocket).
      The Ephemera:   Identify 4-5 small, specific consumer goods or artifacts (e.g., "Tang" Packet, Freeze-Dried Ice Cream, Mission Patches, Apollo 11 Manual).
      The Timeline:   Identify the key visual evolution steps (e.g., Sputnik -> Lunar Module -> Shuttle).

  2. The Immutable Container (The Corner Stage):  
      Geometry:   The book is NOT lying flat. It is standing upright, opened to form a   Strict 90-Degree Corner  .
         Vertical Wall:  The back cover/pages standing straight up.
         Horizontal Floor:  The front cover/pages lying flat.
      The Anchor:   The "Totem" object (Rocket) stands   inside the spine crease  , acting as the structural pillar holding the book open.
      Paper Texture:   The pages must look thick, rough, and heavily aged (like an 1800s manuscript).

  3. The Vertical Plane (The Da Vinci Sketchbook):  
      Density:     MAXIMUM.   Do not leave white space.
      Style:   Sepia-tone   Pen & Ink Technical Drawings  .
      Content:   The background should be a chaotic but organized collage of diagrams, timelines, and schematics. It should look like a scientist's field notes.
      Text:   A bold, formal Serif Title at the top (e.g., "{argument name="title" default="HISTORY OF SPACE EXPLORATION"}").

  4. The Horizontal Plane (The Physical Clutter):  
      Transition:   The Totem (Rocket) seamlessly transitions from a drawing on the wall to a   Physical 3D Model   on the floor.
      The Scatter:   The "Ephemera" props are   scattered and overlapping   on the floor page. They should not be neatly arranged.
         Material Contrast:  The props must look like shiny plastic, crinkled foil, and fabric patches. This clashes with the matte paper.
         Scale:  A tiny 1:64 scale human figure (e.g., Astronaut) stands next to the massive Totem for scale.

  5. Visual Syntax:  
      Background:     Void Black.   The book floats in infinite darkness.   DO NOT render studio equipment, lamps, or tables.  
      Lighting:   "Museum Display" lighting. A focused beam hits the Totem, creating a long shadow against the back page sketches.
      Depth:   The 3D objects must cast hard shadows onto the 2D paper to sell the optical illusion.

  Output:   1:1 Aspect Ratio, Macro Photography, High Textural Contrast (Paper vs. Plastic). </instructions>

{
  "prompt":"Create a highly detailed isometric 3D render of a miniature solarpunk cozy room diorama. The style should be whimsical with a clay texture finish. The room features a glass ceiling with integrated solar panels, abundant hanging plants, a sleeping cat on a window hammock, and a glowing vintage computer setup. Warm, golden hour lighting casting long shadows. 8k resolution, Octane render."
}

A hand-carved wooden miniature figure of {argument name="subject name" default="[NAME]"}, shaped with visible knife marks, natural grain texture, and smooth unfinished edges. Placed on a workshop table with carving tools, wood shavings, and soft warm directional lighting. 1080×1080.

Ultra-high quality photorealistic 3D character render presented as a 3x3 image grid (nine frames total), featuring the SAME adult female human subject in nine different poses. Minimalist studio environment with a smooth, seamless light-gray floor and background, no props, no scenery, no text. 

CAMERA & STYLE:
High-angle and slightly top-down perspectives dominate across the grid. Subtle wide-angle lens feel. Photorealistic cinematic 3D render with clean shading, high detail, realistic skin and fabric textures. Professional editorial character showcase. 

POSES GRID ORDER – SAME WOMAN:
1. Squatting slightly with knees bent, arms resting near thighs, looking up at the camera. 
2. Standing upright, relaxed posture, head slightly turned. 
3. Sitting with one knee raised, composed introspective pose. 
4. Standing with hands resting confidently at the waist. 
5. Kneeling and leaning slightly forward, head tilted up, engaged gaze. 
6. Standing with one arm raised gently as if signaling or acknowledging. 
7. Sitting cross-legged, calm and composed posture. 
8. Standing while extending one arm toward the camera in an elegant, interactive gesture. 
9. Lying flat on the back, face looking straight upward, symmetrical composition. 

MOOD & PURPOSE:
Elegant, confident, glamorous, composed. Feels like a professional editorial character turnaround and pose study used for fashion visualization, cinematic previsualization, or high-end portrait rendering. 

RENDER QUALITY:
Ultra-detailed, clean topology, realistic anatomy, smooth gradients, sharp focus, studio-grade output. No noise, no blur, no artifacts. 

CONSISTENCY RULES:
Same face, same body, same hair, same makeup, same outfit, same accessories across all nine frames. No variation drift. 

NEGATIVE PROMPTS:
No background scenery, no environment elements, no text, no logos, no extra characters, no clothing changes, no face variation, no color shifts, no stylization drift, no cartoon or anime look, no distortion, no anatomy errors.

Create a full-body 2D vector-style character illustration with clean lines and smooth flat shading. Accurately study and replicate the original person’s facial structure, body proportions, skin tone, hairstyle, and expression from the uploaded reference image.
Match the exact {argument name="outfit details" default="outfit, colors, fabric feel, and accessories"}, keeping the same pose and posture.
Style should be {argument name="style" default="modern, minimal, and polished"} with crisp outlines.
Output as a high-quality transparent PNG, showing only the character with no background.

A beautiful, highly detailed, photorealistic image of a female cyberpunk character, neon lights, city background, cinematic lighting, 8k, hyper-detailed, intricate, sharp focus, art by {argument name="artist" default="Greg Rutkowski"}, {argument name="style" default="cyberpunk"}, {argument name="color scheme" default="blue and purple"}